Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Quotation/Angle brackets/Apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Counseling
    -0.07
     terrorism
    -0.06
    Recv
    -0.06
    Gap
    -0.06
    .host
    -0.06
    앙
    -0.06
     directs
    -0.06
     revive
    -0.06
    323
    -0.06
     anytime
    -0.06
    POSITIVE LOGITS
    achelor
    0.07
     Squ
    0.07
    (er
    0.06
     SplashScreen
    0.06
    _KeyPress
    0.06
    ··
    0.06
     Anita
    0.06
    _<?
    0.06
    _tweet
    0.06
    ubah
    0.06
    Act Density 0.029%

    No Known Activations